Disclosure of Invention
In view of the above, the present invention has been developed to provide a method, apparatus and system for implementing a network show that overcomes, or at least partially solves, the above-mentioned problems.
According to an aspect of the present invention, there is provided a method for implementing network performance, applied to a performer side, including:
acquiring a video stream about an actor;
generating descriptive information for the performer from the video stream;
and sending the description information to a server so that the server forwards the description information to a performance content display terminal, and generating and displaying performance content by the performance content display terminal according to the description information.
Optionally, the acquiring a video stream about the performer comprises:
and acquiring the video stream acquired by the video acquisition equipment, and/or generating the video stream according to the selected video file.
Optionally, the generating performance content according to the description information includes:
and driving a performance model to generate performance content according to the description information.
Optionally, the method further comprises:
selecting a performance model for generating performance content from a preset performance model library according to the received performance model selection request;
notifying the server of the selected performance model to cause the server to notify the performance content presentation terminal of the selected performance model.
Optionally, the generating descriptive information for the performer from the video stream comprises:
identifying a performer from the video stream;
further identifying the pose of the performer according to the identified performer;
and calculating the driving parameters of the performance model according to the recognized postures.
Optionally, the performance model is a 2D animated model or a 3D animated model.
Optionally, the method further comprises:
acquiring an audio stream about an actor;
and sending the audio stream to the server so that the server forwards the audio stream to a performance content display terminal, and generating and displaying performance content by the performance content display terminal according to the description information and the audio stream.
Optionally, the obtaining an audio stream about the performer comprises:
and separating the audio stream from the video stream, or acquiring the audio stream collected by the audio collecting equipment.
Optionally, the method further comprises:
selecting a performance scene from a preset performance scene library according to a received performance scene selection request;
and informing the server of the selected performance scene so as to enable the server to inform the performance content display terminal of the selected performance scene, and generating and displaying performance content by the performance content display terminal according to the performance scene and the description information.
According to another aspect of the present invention, there is provided a method for implementing a network performance, applied to a viewer side, including:
selecting an actor;
receiving description information of the performer sent by a server;
and generating and displaying the performance content according to the description information.
Optionally, the generating performance content according to the description information includes:
and driving a performance model to generate performance content according to the description information.
Optionally, the method further comprises:
selecting a performance model for generating performance content from a preset performance model library according to the performance model notified by the server;
or,
receiving a performance model issued by the server;
or,
and selecting a performance model for generating performance content from a preset performance model library according to the received performance model selection request.
Optionally, the description information is a driving parameter of the performance model calculated after the posture of the performer is recognized.
Optionally, the performance model is a 2D animated model or a 3D animated model.
Optionally, the method further comprises: receiving an audio stream about the performer sent by the server;
the generating performance content according to the description information further comprises: and generating performance content according to the audio stream and the description information.
Optionally, the generating performance content according to the description information further includes:
generating performance content according to the determined performance scene and the description information; wherein the performance scene is determined according to any one of the following modes:
selecting a performance scene for generating performance content from a preset performance scene library according to the performance scene notified by the server;
receiving a performance scene sent by the server;
and selecting the performance scene for generating the performance content from a preset performance scene library according to the received performance scene selection request.
According to another aspect of the present invention, there is provided an apparatus for implementing network performance, applied to a performer side, including:
an acquisition unit adapted to acquire a video stream about an actor;
a generating unit adapted to generate descriptive information for the performer from the video stream;
and the sending unit is suitable for sending the description information to the server so as to enable the server to forward the description information to the performance content display terminal, and the performance content display terminal generates and displays the performance content according to the description information.
Optionally, the obtaining unit is adapted to obtain a video stream collected by the video collecting device, and/or generate a video stream according to the selected video file.
Optionally, the generating unit is adapted to drive a performance model to generate performance content according to the description information.
Optionally, the apparatus further comprises:
a performance model selection unit adapted to select a performance model for generating performance contents from a preset performance model library according to the received performance model selection request;
a performance model notification unit adapted to notify the server of the selected performance model to cause the server to notify the performance content presentation terminal of the selected performance model.
Optionally, the generating unit is adapted to identify a performer from the video stream; further identifying the pose of the performer according to the identified performer; and calculating the driving parameters of the performance model according to the recognized postures.
Optionally, the performance model is a 2D animated model or a 3D animated model.
Optionally, the obtaining unit is further adapted to obtain an audio stream about the performer;
the sending unit is further adapted to send the audio stream to the server, so that the server forwards the audio stream to a performance content display terminal, and the performance content display terminal generates and displays performance content according to the description information and the audio stream.
Optionally, the obtaining unit is adapted to separate an audio stream from the video stream, or obtain an audio stream captured by an audio capturing device.
Optionally, the apparatus further comprises:
the performance scene selection unit is suitable for selecting a performance scene from a preset performance scene library according to the received performance scene selection request;
and the performance scene notification unit is suitable for notifying the server of the selected performance scene so as to enable the server to notify the performance content display terminal of the selected performance scene, and the performance content display terminal generates and displays the performance content according to the performance scene and the description information.
According to still another aspect of the present invention, there is provided an apparatus for implementing a network performance, applied to a viewer side, including:
a selection unit adapted to select an actor;
the receiving unit is suitable for receiving the description information of the performer sent by the server;
and the generating unit is suitable for generating and displaying the performance content according to the description information.
Optionally, the generating unit is adapted to drive a performance model to generate performance content according to the description information.
Optionally, the generating unit is adapted to determine the performance model according to any one of the following: selecting a performance model for generating performance content from a preset performance model library according to the performance model notified by the server; receiving a performance model issued by the server; and selecting a performance model for generating performance content from a preset performance model library according to the received performance model selection request.
Optionally, the description information is a driving parameter of the performance model calculated after the posture of the performer is recognized.
Optionally, the performance model is a 2D animated model or a 3D animated model.
Optionally, the receiving unit is further adapted to receive an audio stream about the performer sent by the server;
the generating unit is further adapted to generate performance content according to the audio stream and the description information.
Optionally, the generating unit is adapted to generate performance content according to the determined performance scene and the description information; wherein the performance scene is determined according to any one of the following modes:
selecting a performance scene for generating performance content from a preset performance scene library according to the performance scene notified by the server;
receiving a performance scene sent by the server;
and selecting the performance scene for generating the performance content from a preset performance scene library according to the received performance scene selection request.
According to still another aspect of the present invention, there is provided a network performance implementation system, comprising a server, one or more implementation apparatuses applied to a network performance on a performer side as described in any one of the above, and one or more implementation apparatuses applied to a network performance on a viewer side as described in any one of the above.
According to still another aspect of the present invention, there is provided an intelligent terminal including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform a method as any one of the above.
According to a further aspect of the invention, there is provided a computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement a method as any one of the above.
According to the technical scheme, after the video stream about the performer is acquired, the description information about the performer is generated based on the video stream, the description information is sent to the server, so that the server forwards the description information to the performance content display terminal, and the performance content is generated and displayed by the performance content display terminal according to the description information. According to the technical scheme, the traditional implementation mode of transmitting the video stream is changed into the mode of only transmitting the description information of the performer, so that the resource consumption of network transmission is greatly reduced, and the pause caused by network jitter during the display of the network performance is effectively reduced.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Fig. 1 is a flow chart illustrating a method for implementing a network performance according to an embodiment of the present invention, which can be applied to a performer side, for example, a mobile phone of the performer. As shown in fig. 1, the method includes:
in step S110, a video stream about the performer is acquired. This step does not send the video stream to the server over the network.
In step S120, descriptive information about the performer is generated from the video stream.
And step S130, sending the description information to the server so that the server forwards the description information to the performance content display terminal, and the performance content display terminal generates and displays the performance content according to the description information.
In fact, this is a way of regenerating the performance content, the performance content seen by the viewer is not the actual content performed by the performer, but most of the two are the same, which has good effect on the performance that needs to show the body movement way, for example, if the user only wants to learn the decomposition action of a certain dance, then it is actually performed by a human or a robot, there is not much difference, only the characteristics of each action need to be learned, and these characteristics can be realized by the description information.
It can be seen that, in the method shown in fig. 1, after the video stream about the performer is acquired, the description information about the performer is generated based on the video stream, and the description information is sent to the server, so that the server forwards the description information to the performance content display terminal, and the performance content display terminal generates and displays the performance content according to the description information. According to the technical scheme, the traditional implementation mode of transmitting the video stream is changed into the mode of only transmitting the description information of the performer, so that the resource consumption of network transmission is greatly reduced, and the pause caused by network jitter during the display of the network performance is effectively reduced.
In one embodiment of the present invention, the above method, wherein acquiring the video stream about the performer comprises: and acquiring the video stream acquired by the video acquisition equipment, and/or generating the video stream according to the selected video file.
For example, a camera of a mobile phone is used to capture a video stream, the video stream is input from an external camera, and the video stream is generated according to a recorded and edited video file.
In an embodiment of the present invention, the generating the performance content according to the description information includes: and driving the performance model to generate performance content according to the description information. Specifically, in one embodiment of the present invention, in the above method, the performance model is a 2D animation model or a 3D animation model.
In this way, both a reduction in data traffic and protection of the privacy of the performers can be achieved, for example many performers who are not expected to be exposed to the face, especially some underage anchor. Dance motion teaching can also be implemented, for example, with a robot as a performance model.
Of course, depending on the content of the performance, different performance models may be selected, some suitable for displaying body posture, some suitable for displaying expression, etc. In an embodiment of the present invention, the method further includes: selecting a performance model for generating performance content from a preset performance model library according to the received performance model selection request; and informing the server of the selected performance model, so that the server informs the performance content display terminal of the selected performance model.
That is, a performance model library can be preset locally, or such a performance model library is preset at a server end, and a corresponding list is presented locally; the performer can then select the appropriate performance model for presentation at the viewer's performance content presentation terminal.
In an embodiment of the present invention, the above method, wherein generating the descriptive information about the performer from the video stream includes: identifying a performer from the video stream; further identifying the pose of the performer according to the identified performer; and calculating the driving parameters of the performance model according to the recognized postures.
In the embodiment of the present invention, the performer may be a human, a panda, a robot, or the like. Therefore, different performer identification algorithms can be selected according to different performers; and the recognition of the gesture is usually realized by another set of algorithm. Thus, posture identifications such as the coordinates of feature points of five sense organs, bone parameters and the like can be obtained, and the posture identifications are mapped on the performance model, so that the driving parameters of the performance model are obtained.
For example, it is recognized that the right arm bending angle of the performer is 90 degrees, and the right arm bending angle of the corresponding performance model is also 90 degrees. The mirror transformation can be carried out according to the requirements of users, which is a ubiquitous requirement in dance performances.
In an embodiment of the present invention, the method further includes: acquiring an audio stream about an actor; and sending the audio stream to the server so that the server forwards the audio stream to the performance content display terminal, and generating and displaying the performance content by the performance content display terminal according to the description information and the audio stream.
Sometimes, the content of the performer's performance also includes sound, such as a singing performance. The audio stream may also be sent to a server for subsequent presentation. In one embodiment of the present invention, the above method, wherein acquiring the audio stream about the performer comprises: and separating the audio stream from the video stream, or acquiring the audio stream collected by the audio collecting equipment.
For example, an audio stream is captured by a microphone and a video stream is captured by a camera, so that the two do not interfere with each other; in another case, the audio stream is included in the video stream, in which case the separation process is performed.
In an embodiment of the present invention, the method further includes: selecting a performance scene from a preset performance scene library according to a received performance scene selection request; and informing the server of the selected performance scene so that the server informs the performance content display terminal of the selected performance scene, and generating and displaying the performance content by the performance content display terminal according to the performance scene and the description information.
In the present embodiment, the performer can freely select the background of the performance, for example, the performer wants to perform a dance in the moon, but the current day is cloudy, which cannot be realized by the prior art. In this case, the performance scene can be arbitrarily selected.
Fig. 2 is a flow chart illustrating another implementation method of network performance according to an embodiment of the present invention, which can be applied to a viewer side, for example, a performance content display terminal of a viewer. As shown in fig. 2, the method includes:
in step S210, an actor is selected. For example, the viewer selects which live room to enter to view the webcast.
Step S220, receiving the description information of the performer sent by the server.
Instead of receiving a video stream in the prior art, which is received in the live broadcast, in this embodiment, description information is received.
And step S230, generating and displaying the performance content according to the description information.
In fact, this is the above-mentioned way of regenerating the performance content, and the performance content seen by the viewer is not the actual content performed by the performer, but most of the two are the same, which has good effect on the performance that needs to show the body movement way, for example, if the user only wants to learn the decomposition action of a certain dance, then it is actually performed by a person or performed by a robot, and there is no great difference, and only the characteristics of each action need to be learned, and these characteristics can be realized by the description information.
It can be seen that the method shown in fig. 2, after determining the performer, obtains the description information of the performer from the server, and generates and displays the performance content according to the description information. According to the technical scheme, the traditional implementation mode of transmitting the video stream is changed into the mode of only transmitting the description information of the performer, so that the resource consumption of network transmission is greatly reduced, and the pause caused by network jitter during the display of the network performance is effectively reduced.
In an embodiment of the present invention, the generating the performance content according to the description information includes: and driving the performance model to generate performance content according to the description information. Specifically, in one embodiment of the present invention, in the above method, the performance model is a 2D animation model or a 3D animation model.
In this way, both a reduction in data traffic and protection of the privacy of the performers can be achieved, for example many performers who are not expected to be exposed to the face, especially some underage anchor. Dance motion teaching can also be implemented, for example, with a robot as a performance model.
In an embodiment of the present invention, the method further includes: selecting a performance model for generating performance content from a preset performance model library according to the performance model notified by the server; or, receiving a performance model issued by the server; or selecting the performance model for generating the performance content from a preset performance model library according to the received performance model selection request.
In the embodiment, three determination modes of performance models are provided; one is that the server informs which performance model is used, and selects the corresponding performance model from the local performance model library; if the local performance model base does not have the corresponding performance model, the corresponding performance model can be obtained from the server and stored locally; both of these ways are determined by the performer which performance model to use. In some cases, the viewer may also be allowed to determine himself or herself what performance model to use.
In an embodiment of the present invention, in the above method, the description information is a driving parameter of the performance model calculated after the posture of the performer is recognized.
In the embodiment of the present invention, the performer may be a human, a panda, a robot, or the like. Therefore, different performer identification algorithms can be selected according to different performers; and the recognition of the gesture is usually realized by another set of algorithm. Thus, posture identifications such as the coordinates of feature points of five sense organs, bone parameters and the like can be obtained, and the posture identifications are mapped on the performance model, so that the driving parameters of the performance model are obtained.
For example, it is recognized that the right arm bending angle of the performer is 90 degrees, and the right arm bending angle of the corresponding performance model is also 90 degrees. The mirror transformation can be carried out according to the requirements of users, which is a ubiquitous requirement in dance performances.
In an embodiment of the present invention, the method further includes: receiving an audio stream about the performer sent by the server; generating the performance content according to the description information further includes: the performance content is generated from the audio stream and the descriptive information.
Sometimes, the content of the performer's performance also includes sound, such as a singing performance. Therefore, the performer can also send the audio stream to the server, and the performance content display terminal on the viewer side generates performance content according to the audio stream and the description information for subsequent display.
In an embodiment of the present invention, in the method, generating the performance content according to the description information further includes: generating performance contents according to the determined performance scene and the description information; wherein the performance scene is determined according to any one of the following modes: selecting a performance scene for generating performance content from a preset performance scene library according to the performance scene notified by the server; receiving a performance scene sent by a server; and selecting the performance scene for generating the performance content from a preset performance scene library according to the received performance scene selection request.
Similar to the previous embodiment, in this embodiment, the performer can also freely select the background of the performance, and if the local performance scene library of the performance content display terminal of the viewer has a corresponding performance scene, the corresponding performance scene is selected, and the corresponding performance scene is not issued from the server; in some cases, the viewer himself is allowed to determine what performance scenario to use.
Fig. 3 is a schematic structural diagram of an apparatus for implementing a network performance according to an embodiment of the present invention, which can be applied to a performer side, for example, a mobile phone of the performer. As shown in fig. 3, the apparatus 300 for implementing a network performance includes:
the acquisition unit 310 is adapted to acquire a video stream regarding the performer and not to send the video stream to the server over the network.
A generating unit 320 adapted to generate descriptive information for the performer from the video stream.
And the sending unit 330 is adapted to send the description information to the server, so that the server forwards the description information to the performance content exhibition terminal, and the performance content exhibition terminal generates and exhibits the performance content according to the description information.
In fact, this is a way of regenerating the performance content, the performance content seen by the viewer is not the actual content performed by the performer, but most of the two are the same, which has good effect on the performance that needs to show the body movement way, for example, if the user only wants to learn the decomposition action of a certain dance, then it is actually performed by a human or a robot, there is not much difference, only the characteristics of each action need to be learned, and these characteristics can be realized by the description information.
It can be seen that, after the video stream about the performer is acquired, the device shown in fig. 3 generates the description information about the performer based on the video stream, and sends the description information to the server, so that the server forwards the description information to the performance content display terminal, and the performance content display terminal generates and displays the performance content according to the description information. According to the technical scheme, the traditional implementation mode of transmitting the video stream is changed into the mode of only transmitting the description information of the performer, so that the resource consumption of network transmission is greatly reduced, and the pause caused by network jitter during the display of the network performance is effectively reduced.
In an embodiment of the present invention, in the above apparatus, the obtaining unit 310 is adapted to obtain a video stream captured by a video capturing device, and/or generate a video stream according to a selected video file.
In an embodiment of the present invention, in the above apparatus, the generating unit 320 is adapted to drive the performance model to generate the performance content according to the description information.
In an embodiment of the present invention, the apparatus further includes: a performance model selection unit adapted to select a performance model for generating performance contents from a preset performance model library according to the received performance model selection request; and a performance model notification unit adapted to notify the server of the selected performance model so as to cause the server to notify the performance content presentation terminal of the selected performance model.
In an embodiment of the present invention, in the above apparatus, the generating unit 320 is adapted to identify the performer from the video stream; further identifying the pose of the performer according to the identified performer; and calculating the driving parameters of the performance model according to the recognized postures.
In one embodiment of the present invention, in the above apparatus, the performance model is a 2D animation model or a 3D animation model.
In an embodiment of the present invention, in the above apparatus, the obtaining unit 310 is further adapted to obtain an audio stream about the performer; the sending unit 330 is further adapted to send the audio stream to the server, so that the server forwards the audio stream to the performance content exhibition terminal, and the performance content exhibition terminal generates and exhibits the performance content according to the description information and the audio stream.
In an embodiment of the present invention, in the above apparatus, the obtaining unit 310 is adapted to separate an audio stream from a video stream, or obtain an audio stream captured by an audio capturing device.
In an embodiment of the present invention, the apparatus further includes: the performance scene selection unit is suitable for selecting a performance scene from a preset performance scene library according to the received performance scene selection request; and the performance scene notification unit is suitable for notifying the server of the selected performance scene so as to enable the server to notify the performance content display terminal of the selected performance scene, and the performance content is generated and displayed by the performance content display terminal according to the performance scene and the description information.
Fig. 4 is a schematic structural diagram of another apparatus for implementing a network performance according to an embodiment of the present invention, which can be applied to a viewer side, for example, a performance content display terminal of a viewer. As shown in fig. 4, the apparatus 400 for implementing a network performance includes:
a selection unit 410 adapted to select an actor. For example, the viewer selects which live room to enter to view the webcast.
The receiving unit 420 is adapted to receive the description information of the actor sent by the server. Instead of receiving a video stream in the prior art, which is received in the live broadcast, in this embodiment, description information is received.
And the generating unit 430 is suitable for generating and displaying the performance content according to the description information.
In fact, this is the above-mentioned way of regenerating the performance content, and the performance content seen by the viewer is not the actual content performed by the performer, but most of the two are the same, which has good effect on the performance that needs to show the body movement way, for example, if the user only wants to learn the decomposition action of a certain dance, then it is actually performed by a person or performed by a robot, and there is no great difference, and only the characteristics of each action need to be learned, and these characteristics can be realized by the description information.
As can be seen, the apparatus shown in fig. 4, after determining the performer, acquires description information of the performer from the server, and generates and displays performance content according to the description information. According to the technical scheme, the traditional implementation mode of transmitting the video stream is changed into the mode of only transmitting the description information of the performer, so that the resource consumption of network transmission is greatly reduced, and the pause caused by network jitter during the display of the network performance is effectively reduced.
In an embodiment of the present invention, in the above apparatus, the generating unit 430 is adapted to drive the performance model to generate the performance content according to the description information.
In an embodiment of the present invention, in the above apparatus, the generating unit 430 is adapted to determine the performance model according to any one of the following manners: selecting a performance model for generating performance content from a preset performance model library according to the performance model notified by the server; receiving a performance model issued by a server; and selecting a performance model for generating performance content from a preset performance model library according to the received performance model selection request.
In one embodiment of the present invention, in the above apparatus, the description information is a driving parameter of the performance model calculated after the posture of the performer is recognized.
In one embodiment of the present invention, in the above apparatus, the performance model is a 2D animation model or a 3D animation model.
In an embodiment of the present invention, in the above apparatus, the receiving unit 420 is further adapted to receive an audio stream about the performer sent by the server; the generating unit 430 is further adapted to generate the performance content from the audio stream and the description information.
In an embodiment of the present invention, in the above apparatus, the generating unit 430 is adapted to generate the performance content according to the determined performance scene and the description information; wherein the performance scene is determined according to any one of the following modes: selecting a performance scene for generating performance content from a preset performance scene library according to the performance scene notified by the server; receiving a performance scene sent by a server; and selecting the performance scene for generating the performance content from a preset performance scene library according to the received performance scene selection request.
It should be noted that, for the specific implementation of each apparatus embodiment, reference may be made to the specific implementation of the corresponding method embodiment, which is not described herein again.
Fig. 5 is a schematic structural diagram of a system for implementing a network show according to an embodiment of the present invention. As shown in fig. 5, the system 500 for implementing a network performance includes a server 510, one or more apparatuses 300 for implementing a network performance as in any of the above embodiments, and one or more apparatuses 400 for implementing a network performance as in any of the above embodiments.
In summary, according to the technical solution of the present invention, after the video stream about the performer is acquired, the description information about the performer is generated based on the video stream, and the description information is sent to the server, so that the server forwards the description information to the performance content display terminal, and the performance content display terminal generates and displays the performance content according to the description information. According to the technical scheme, the traditional implementation mode of transmitting the video stream is changed into the mode of only transmitting the description information of the performer, so that the resource consumption of network transmission is greatly reduced, and the pause caused by network jitter during the display of the network performance is effectively reduced.
It should be noted that:
the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of an implementation apparatus and system of a network performance according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
For example, fig. 6 shows a schematic structural diagram of an intelligent terminal according to an embodiment of the present invention. The intelligent terminal comprises a processor 610 and a memory 620 arranged to store computer executable instructions (computer readable program code). The memory 620 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 620 has a storage space 630 storing computer readable program code 631 for performing any of the method steps described above. For example, the memory space 630 for storing the computer readable program code may comprise respective computer readable program codes 631 for respectively implementing the various steps in the above method. The computer readable program code 631 may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a computer readable storage medium such as described in fig. 7. Fig. 7 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention. The computer readable storage medium 700, in which a computer readable program code 631 for performing the steps of the method according to the invention is stored, is readable by the processor 610 of the smart terminal 600, and when the computer readable program code 631 is executed by the smart terminal 600, causes the smart terminal 600 to perform the steps of the method described above, and in particular the computer readable program code 631 stored by the computer readable storage medium may perform the method shown in any of the embodiments described above. The computer readable program code 631 may be compressed in a suitable form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The embodiment of the invention discloses A1, a method for realizing network performance, which is applied to a performer side and comprises the following steps:
acquiring a video stream about an actor;
generating descriptive information for the performer from the video stream;
and sending the description information to a server so that the server forwards the description information to a performance content display terminal, and generating and displaying performance content by the performance content display terminal according to the description information.
A2, the method as in a1, wherein the acquiring a video stream about an actor comprises:
and acquiring the video stream acquired by the video acquisition equipment, and/or generating the video stream according to the selected video file.
A3, the method as in a1, wherein the generating performance content according to the descriptive information comprises:
and driving a performance model to generate performance content according to the description information.
A4, the method of A3, wherein the method further comprises:
selecting a performance model for generating performance content from a preset performance model library according to the received performance model selection request;
notifying the server of the selected performance model to cause the server to notify the performance content presentation terminal of the selected performance model.
A5, the method as in A3, wherein the generating descriptive information for the performer from the video stream comprises:
identifying a performer from the video stream;
further identifying the pose of the performer according to the identified performer;
and calculating the driving parameters of the performance model according to the recognized postures.
A6, the method of A3, wherein the performance model is a 2D animated model or A3D animated model.
A7, the method of a1, wherein the method further comprises:
acquiring an audio stream about an actor;
and sending the audio stream to the server so that the server forwards the audio stream to a performance content display terminal, and generating and displaying performance content by the performance content display terminal according to the description information and the audio stream.
A8, the method as in a7, wherein the obtaining an audio stream about an actor comprises:
and separating the audio stream from the video stream, or acquiring the audio stream collected by the audio collecting equipment.
A9, the method of a1, wherein the method further comprises:
selecting a performance scene from a preset performance scene library according to a received performance scene selection request;
and informing the server of the selected performance scene so as to enable the server to inform the performance content display terminal of the selected performance scene, and generating and displaying performance content by the performance content display terminal according to the performance scene and the description information.
The embodiment of the invention also discloses B10 and a method for realizing network performance, which is applied to a viewer side and comprises the following steps:
selecting an actor;
receiving description information of the performer sent by a server;
and generating and displaying the performance content according to the description information.
B11, the method according to B10, wherein the generating the performance content according to the description information comprises:
and driving a performance model to generate performance content according to the description information.
B12, the method according to B11, wherein the method further comprises:
selecting a performance model for generating performance content from a preset performance model library according to the performance model notified by the server;
or,
receiving a performance model issued by the server;
or,
and selecting a performance model for generating performance content from a preset performance model library according to the received performance model selection request.
B13, the method according to B11, wherein the description information is driving parameters of the performance model calculated after the posture of the performer is recognized.
B14, the method of B11, wherein the performance model is a 2D animated model or a 3D animated model.
B15, the method according to B10, wherein the method further comprises: receiving an audio stream about the performer sent by the server;
the generating performance content according to the description information further comprises: and generating performance content according to the audio stream and the description information.
B16, the method of B10, wherein the generating performance content according to the descriptive information further comprises:
generating performance content according to the determined performance scene and the description information; wherein the performance scene is determined according to any one of the following modes:
selecting a performance scene for generating performance content from a preset performance scene library according to the performance scene notified by the server;
receiving a performance scene sent by the server;
and selecting the performance scene for generating the performance content from a preset performance scene library according to the received performance scene selection request.
The embodiment of the invention also discloses C17, a device for realizing network performance, which is applied to the side of a performer, and comprises:
an acquisition unit adapted to acquire a video stream about an actor;
a generating unit adapted to generate descriptive information for the performer from the video stream;
and the sending unit is suitable for sending the description information to the server so as to enable the server to forward the description information to the performance content display terminal, and the performance content display terminal generates and displays the performance content according to the description information.
C18, the device of C17, wherein,
the acquisition unit is suitable for acquiring the video stream acquired by the video acquisition equipment and/or generating the video stream according to the selected video file.
C19, the device of C17, wherein,
the generating unit is suitable for driving a performance model to generate performance content according to the description information.
C20, the apparatus of C19, wherein the apparatus further comprises:
a performance model selection unit adapted to select a performance model for generating performance contents from a preset performance model library according to the received performance model selection request;
a performance model notification unit adapted to notify the server of the selected performance model to cause the server to notify the performance content presentation terminal of the selected performance model.
C21, the device of C19, wherein,
the generating unit is suitable for identifying performers from the video stream; further identifying the pose of the performer according to the identified performer; and calculating the driving parameters of the performance model according to the recognized postures.
C22, the apparatus of C19, wherein the performance model is a 2D animated model or a 3D animated model.
C23, the device of C17, wherein,
the acquisition unit is further adapted to acquire an audio stream about the performer;
the sending unit is further adapted to send the audio stream to the server, so that the server forwards the audio stream to a performance content display terminal, and the performance content display terminal generates and displays performance content according to the description information and the audio stream.
C24, the device of C23, wherein,
the obtaining unit is suitable for separating an audio stream from the video stream or obtaining the audio stream collected by an audio collecting device.
C25, the apparatus of C17, wherein the apparatus further comprises:
the performance scene selection unit is suitable for selecting a performance scene from a preset performance scene library according to the received performance scene selection request;
and the performance scene notification unit is suitable for notifying the server of the selected performance scene so as to enable the server to notify the performance content display terminal of the selected performance scene, and the performance content display terminal generates and displays the performance content according to the performance scene and the description information.
The embodiment of the invention also discloses D26, a device for realizing network performance, which is applied to a viewer side and comprises:
a selection unit adapted to select an actor;
the receiving unit is suitable for receiving the description information of the performer sent by the server;
and the generating unit is suitable for generating and displaying the performance content according to the description information.
D27, the device of D26, wherein,
the generating unit is suitable for driving a performance model to generate performance content according to the description information.
D28, the device of D27, wherein,
the generation unit is suitable for determining the performance model according to any one of the following modes: selecting a performance model for generating performance content from a preset performance model library according to the performance model notified by the server; receiving a performance model issued by the server; and selecting a performance model for generating performance content from a preset performance model library according to the received performance model selection request.
D29, the device as in D27, wherein the description information is driving parameters of the performance model calculated after the posture of the performer is recognized.
D30, the apparatus of D27, wherein the performance model is a 2D animated model or a 3D animated model.
D31, the device of D26, wherein,
the receiving unit is also suitable for receiving the audio stream about the performer sent by the server;
the generating unit is further adapted to generate performance content according to the audio stream and the description information.
D32, the device of D26, wherein,
the generating unit is suitable for generating performance contents according to the determined performance scenes and the description information; wherein the performance scene is determined according to any one of the following modes:
selecting a performance scene for generating performance content from a preset performance scene library according to the performance scene notified by the server;
receiving a performance scene sent by the server;
and selecting the performance scene for generating the performance content from a preset performance scene library according to the received performance scene selection request.
The embodiment of the invention also discloses E33, and a network performance implementation system, which comprises a server, one or more network performance implementation devices as described in any one of C17-C25, and one or more network performance implementation devices as described in any one of D26-D32.
The embodiment of the invention also discloses F34 and an intelligent terminal, wherein the intelligent terminal comprises: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform a method as any one of a1-a9 or cause the processor to perform a method as any one of a10-a 16.
Embodiments of the invention also disclose G35, a computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the method as described in any of a1-a9, or implement the method as described in any of a10-a 16.